Applied Machine Learning Introduction 1 APPLIED MACHINE LEARNING - PowerPoint PPT Presentation

APPLIED MACHINE LEARNING Applied Machine Learning Introduction 1

APPLIED MACHINE LEARNING Practicalities Slides and exercises will be posted on the website of the class the day before class: http://lasa.epfl.ch/teaching/lectures/ML_Msc/index.php http://lasa.epfl.ch/  Teaching  Lectures  Applied Machine Learning Solutions to the exercises will be posted a week after the exercise session.

APPLIED MACHINE LEARNING Practicalities Contact Information of the Instructors

APPLIED MACHINE LEARNING Class Format • Lectures with interactive exercises: 9h15-12h00 • Exercises (In class): 12h15-13h00 • Lectures alternates with Practical session held in C06-C04, see class schedule! ! Practical sessions run from 8h00 to 13h00 with one hour break 10h00-11h00. • Attendance to practical and exercise sessions is highly recommended…. 4

APPLIED MACHINE LEARNING Grading Scheme Practicals (25% of the grade) – done in team of 2 1 report – due 16/12/2016 or 1 oral presentation – December 16/12/2016 Register on doodle links on class website! Written Exam (75% of the grade) 3 hours long Closed book Allowed 1 A4 pages with handwritten notes 5

APPLIED MACHINE LEARNING LASA 6

APPLIED MACHINE LEARNING Pre-requisites Linear Algebra Probability / Statistics  Vector / Matrix notation  Probability Distribution Function  Eigenvalue decomposition  Covariance, Expectation  Linear dependency  Joint, conditional probability  Correlation / Statistical Independence Optimization  Global versus local optima Brief recap of main algorithms in class  Gradient descent  Method of Lagrange Multipliers 7

APPLIED MACHINE LEARNING Class Objectives - To understand the basics of some key algorithms of Machine Learning - To apply some of these algorithms with real data and, by so doing, to understand the limitations of the algorithm for real- time systems - To raise in you enough interest for the field, so that you will later try to learn more about it (advanced class at the doctoral school, search on- line, …) - To have more engineers apply these techniques for robust control, signal processing, prediction, learning, etc. 8

APPLIED MACHINE LEARNING Learning Outcomes Main learning outcomes: By the end of the course, the student must be able to: • Choose an appropriate ML method • Assess / Evaluate an appropriate ML method • Apply an appropriate ML method Transversal skills • Write a scientific or technical report. • Make an oral presentation. 9

APPLIED MACHINE LEARNING Today’s class format • Taxonomy and basic concepts in ML + examples of ML applications • Introduction to Principal Component Analysis 10

APPLIED MACHINE LEARNING Data Mining Pattern recognition with very large amount of high-dimensional data (Several hundreds and more) (Tens of thousands to billions)

APPLIED MACHINE LEARNING Data Mining: examples Mining webpages • Cluster groups of webpage by topics • Cluster links across webpages Other algorithms required:  Fast methods for crawling the web  Text processing (Natural Language Processing)  Understanding semantics Issues: • Domain-specific language / terminology • Foreign languages • Dynamics of web (pages disappear / get created)

APPLIED MACHINE LEARNING Machine Learning: definitions Machine Learning is the field of scientific study that concentrates on induction algorithms and on other algorithms that can be said to ``learn.'' Machine Learning Journal, Kluwer Academic Machine Learning is an area of artificial intelligence involving developing techniques to allow computers to “ learn ”. More specifically, machine learning is a method for creating computer programs by the analysis of data sets, rather than the intuition of engineers. Machine learning overlaps heavily with statistics, since both fields study the analysis of data. Webster Dictionary Machine learning is a branch of statistics and computer science, which studies algorithms and architectures that learn from data sets. WordIQ 13

APPLIED MACHINE LEARNING What is Machine Learning? Machine Learning encompasses a large set of algorithms that aim at inferring information from what is hidden. Independent Component Analysis (ICA) can decompose mixture of signals A. M. Bronstein, M. M. Bronstein, M. Zibulevsky, "On separation of semitransparent dynamic images from static background", Proc. Intl. Conf. on Independent Component Analysis 14 and Blind Signal Separation , pp. 934-940, 2006.

APPLIED MACHINE LEARNING What is Machine Learning? Helps compute automatically information that would take days to do by hand. The mapping can be done through support vector regression  An algorithm we will see in class Noris, B., Nadel, J, Barker, M., Hadjikhani, N. and Billard, A. (2012) Investigating gaze of children with ASD in naturalistic settings . PLOS ONE. 15

APPLIED MACHINE LEARNING What is Machine Learning? The strength of ML algorithms is that they can apply to arbitrary set of data. It can recognizing patterns from what from various source of data. Recognizing human speech. Here this the wave produced when uttering the word “allright”. Modeling time series : Hidden Markov Models be used to recognize complex sounds, including human speech. 16

APPLIED MACHINE LEARNING What is Machine Learning? Same note played by a oboe Piano note (C5 – do) (hautbois) Classification: Two patterns that are different should still be grouped in the same class 17

APPLIED MACHINE LEARNING Why and when do we need learning in Robotics? 18

APPLIED MACHINE LEARNING A typical problem of Robotics Peg and Hole Problem 19

APPLIED MACHINE LEARNING A typical problem of Robotics Peg and Hole Problem 20

APPLIED MACHINE LEARNING A typical problem of Robotics A: Engineer the environment 21

APPLIED MACHINE LEARNING A typical problem of Robotics A: Engineer the environment B: Engineer the body 22

APPLIED MACHINE LEARNING A typical problem of Robotics A: Engineer the environment B: Engineer the body C: Engineer the controller Systematic search  Adaptive control  Learning Machine! 23

APPLIED MACHINE LEARNING To engineer the environment is not always desirable Rather, it is desirable to have a system that is Adaptable to different environments That can generalize across tasks Kronander, Burdet and Billard, Learning PegI n Hole Insertionf rom Human Demonstrations, 2013 24

APPLIED MACHINE LEARNING Problem ROWS 1-3 ROWS 4-6 Make an autonomous robot that Make an autonomous robot that distributes graded assignments cleans dirty dishes in the to a class of students cafeteria A: Engineer the environment B: Engineer the body C: Engineer the controller 25

APPLIED MACHINE LEARNING Machines that learn To engineer the environment is not always desirable Rather, it is desirable to have a system that is adaptable to different environments can generalize across tasks 26

APPLIED MACHINE LEARNING Taxonomy in ML • Supervised learning – where the algorithm learns a function or model that maps a set of inputs to a set of desired outputs. • Unsupervised learning – where the algorithm learns a model that represents a set of inputs without any feedback (no desired output, no external reinforcement). • Reinforcement learning – where the algorithm learns a mechanism that generates a set of outputs from one input in order to maximize a reward value (external and delayed feedback). 27

APPLIED MACHINE LEARNING Supervised learning • Supervised learning relates to a vast group of methods by which one estimates a model from a set of examples,  The system is given the desired output. • When these examples are provided by a human expert, this is referred to robot learning from demonstration; robot programming by demonstration. 28

APPLIED MACHINE LEARNING Supervised learning Where do the eyes look?  Map image of the eyes to point in the camera image Noris, B., Nadel, J, Barker, M., Hadjikhani, N. and Billard, A. (2012) Investigating gaze of children with ASD in naturalistic settings . PLOS ONE. 29

APPLIED MACHINE LEARNING Supervised learning What is sometimes impossible to see for humans is easy for ML to pick. Exploit information not only on the pupil, cornea, but also on wrinkles, eyelids and eyelashed pattern to infer gaze direction. Support Vector Regression can be used Noris, B., Keller, J-B. and Billard, A. (2011) A Wearable Gaze Tracking System for Children in Unconstrained Environments. Computer Vision and Image to learn this mapping Understanding. 30

APPLIED MACHINE LEARNING Supervised learning Output: 50 images of the scene, In grey color 240x320 pixels Learn a function f:    y f x   i 240 320 , x y i 1...50 Input: 50 images of the eyes, In grey color 20x20 pixels   i 20 20 , x x i 1...50 Support Vector Regression can be used Noris, B., Keller, J-B. and Billard, A. (2011) A Wearable Gaze Tracking System for Children in Unconstrained Environments. Computer Vision and Image to learn this mapping Understanding. 31

APPLIED MACHINE LEARNING Unsupervised Learning Unsupervised learning refers to a variety of methods by which a pair of signals y and x are associated but there is no explicit labeling as to which y should be associated to which x. This is often done through association, i.e. through associative learning. 32